Analisis Sentimen Berdasarkan Komentar Publik Terhadap Toko Online Pada Media Sosial Facebook (Studi Kasus: Zalora dan BerryBenka)
Abstract
Maraknya penggunaan jejaring sosial seperti Facebook mendorong munculnya data tekstual yang tidak terbatas, sehingga muncul kebutuhan penyajian informasi tanpa mengurangi nilai dari informasi tersebut. Salah satu pemanfaatan data ini adalah untuk mengetahui opini atau sentimen publik terhadap pelayanan dan produk suatu toko online. Metodologi yang digunakan untuk melakukan analisis sentimen dimulai dari data collecting, preprocessing, feature selection, klasifikasi dan pengukuran akurasi. Metode klasifikasi Naive Bayes, k-NN dan Decision Tree digunakan untuk membandingkan hasil prediksi klasifikasi yang terbaik. Hasil analisis pengujian menunjukkan Naive Bayes memiliki kestabilan akurasi setelah diuji dengan beberapa nilai Frequent Itemset. Naive bayes memiliki rata-rata akurasi 90.3%.Kata kunci: Opini, Sentimen, Preprocessing, Feature Selection, Klasifikasi, Naïve Bayes, k-NN, Decision Tree, Frequent Itemset, AkurasiReferences
Nielsen. (2014). E-Commerce : Evolution or Revolution in the Fast-Moving Consumer Goods World?. United States : New York.
Liu, Bing. (2012). Sentiment Analysis and Opinion Mining. USA : Morgan & Claypool Publishers.
Sentiaji, Aditia Rakhmat., & Bachtiar, Adam Mukaharil. (2014). Analisis Sentimen Terhadap Acara Televisi Berdasarkan Opini Publik. Bandung : Universitas Komputer Indonesia.
Hidayatullah, Ahmad Fathan. (2014). Analisis Sentimen dan Klasifikasi Kategori Terhadap Tokoh Publik pada Twitter. Yogyakarta : Universitas Gajah Mada.
Blanco, Eduardo., & Moldovan, Dan. (2011). Some Issues on Detecting Negation from Text. Journal of Human Language Technology Research Institute. USA : The University of Texas at Dallas.
Moens, Sandy., Aksehirli, Emin., & Goethals, Bart. (2013). Frequent Itemset Mining for Big Data. Belgium : Universiteit Antwerpen.
Han, Jiawei., Kamber, Micheline., & Pei, Jian. (2012). Data Mining Concepts and Techniques (3rd ed.). USA : Simon Frase University.
Downloads
Published
Issue
Section
License
Copyright info for authors
1. Authors hold the copyright in any process, procedure, or article described in the work and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors retain publishing rights to re-use all or portion of the work in different work but can not granting third-party requests for reprinting and republishing the work.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.